Hacker News

As a counterpoint: in a complex project, Fable's "curiosity" may be exactly what you want for an exploration and planning stage - not just for the orchestrator that turns your prompt into different angles with which to explore, but for each subagent whose task is to search the codebase for one of those "angles." If you truly want no stone unturned, letting those subagents spawn their own discoveries, and recursively grow the surface area of the inquiry, then it's quite reasonable to want Fable throughout.

That said, if your project is "do this well-planned thing on a bunch of things in parallel" then you should absolutely be instructing to have subagents "step down" to less curious models. Their output may well be more cohesive as a result!

Spawning a bunch of agents seems to happen randomly. I almost never want this.

This is why I happily use Codex.

I run it basically 24/7 on a ~500k line repo, and only rarely run out of quota before the end of the week.

My experience with Claude Code was very good until about 2.5 months ago, and then it suddenly turned unbelievably terrible for me.

I have not and will hopefully never look back.

I still have PTSD from how ungodly terrible it was that last week of using it.

Sub agents each have to read part of your code base again to get enough context for the task. And if they take too long, your orchestrator's context is no longer in cache so you pay full price for that again once the subagents finish

If you do it sequentially you only read those files approximately once, and everything hits the same prefix cache

> What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result.

Probably because the general purpose subagents inherit the parent model.

I tell Claude explicitly to use Explore subagents, which use Haiku only, now.

Every subagent send the same ~30k system prompts. If you are using fable/opus, that's easily 30% of a 5-hour window for 7 subagent, before doing any work

--disallowedTools Task

for subagents to be cheap/effective, you have to specify the size of those subagents; i.e. right now by default 5.6-sol spawns many 5.6-sol subagents. 5.4-mini as subagent saves me tons of tokens. 5.6-sol audits the work before accepting it, so there's not really a quality issue.

And in my experience the sub agent performance is usually worse than just a single agent.

Did it deploy five AWS m8g.12xlarge instances?

Once I realized that Anthropic is a token merchant, I start to understand Anthropic’s decision more. They are always finding reasons for you to use more tokens through them unless the users revolt or demand some guardrails.

I thought I read somewhere that according to filings for going public, subscription revenue is tiny… like 5%.

Edit: consumer Claude subs are the 5%. I’d bet most all of CC subs lump in under enterprise.

  - API & Enterprise: 75% to 85% of total revenue.
  - Business Subscriptions: Roughly 10% to 15%.
  - Individual Subscriptions: About 5%.

You're making the opposite argument. Anthropic is incentivized to use less tokens in Claude Code because people are paying a fixed monthly fee for subscriptions.

> I use pi btw

Not sure if intentionally meant as a reference, but it gives "I use Arch btw" vibes.

the amount of system prompt wastage going on in orgs is insane. we identified 400k in annual burn for zero value in just one section of our large company.

and the interesting thing about system prompt wastage is its a cost that scales non linearly with subagent use.

> This is supported by the fact that they won't let you use your sub on a different coding agent

I mean, that's a very weak argument? Isn't a much more plausible explanation that with your tooling you'll have more of a lock-in than with just your model?

Thanks, I'm looking forward to this!

I wonder if a lot of the 33k is context, like from recent conversations.

I often find myself annoyed when Opus fixes a typo in a comment and decides to run tests, lints and whenever else it can find to run. Often it will start by stashing current changes just to preemptively check if all tests were passing before. And I can blame myself a bit because my rules do say: verify all changes with tests. But as there is that I in AI that is hyped which you’d think means it knows not to put tomatoes into fruit salad …

> prompts such as “Hey” or “commit” sometimes triggered 30+ tool calls

I read that this is because it wastes time looking through past conversations and other context to figure one what you might want it to do - a less ambiguous prompt would be better.

I use both now and agree they're basically interchangeable.

I appreciate that Codex is open source and OpenAI has explicitly said using the subscription with other agents is ok. OpenAI has been much more consumer-friendly recently.

What settings have you tried since it "became more opaque"? They've got a lot more settings now.

Maybe related to this minimalism, Pi doesn't come with most of the tools an LLM needs to function efficiently or effectively. I get that a blank slate is the paradigm, and you can add whatever you want, but it's too blank IMO.

I was here looking for this comment = )

Read through it an I'm curious whether setting the date and cmd on every system prompt call will cause the cache to invalidate.

I guess the cache would only be invalid if the day changed or the root directory, which would technically happen infrequently enough.

If you really want a minimal agent that you heavily customize, just skip pi (130+ transitive dependencies on the "minimal" pi-coder package) and write your own. You learn a bunch, and it's not hard. You can even ask another LLM to help you get started.

> --system-prompt ""

Doesn't the model need at least a basic system prompt to understand what tools are available?

Yep, have been using this for a long time now. No idea why everyone doesn’t.

Do you start Claude with this option? Or do you send this with every prompt?

I didn’t know you could do this. Is there any analysis of the impact, before and after? I’d love to see some charts of efficacy in real world usage.

This is interesting, because if I start a fresh session of Claude Code right now and run /context, I see the following:

   Opus 4.8 (1M context)
   claude-opus-4-8[1m]
   23k/1m tokens (2%) 

   Estimated usage by category
   System prompt: 3.9k tokens (0.4%)
   System tools: 13.9k tokens (1.4%)
   Custom agents: 235 tokens (0.0%)
   Memory files: 28 tokens (0.0%)
   Skills: 4.9k tokens (0.5%)
   Messages: 8 tokens (0.0%)
   Compact buffer: 3k tokens (0.3%)
   Free space: 974k (97.4%)

We are yet to try Pi!

They sort of are, in that they want subscription users to have clients that behave well with the KV cache etc.

If you don't use a subscription, and pay per token instead, you can easily move to another harness.

Nice!

> When context gets too long, maki compacts history automatically: strips images, thinking blocks, and summarizes older turns.

Don’t the summaries of older turns effectively invalidate the context cache, such that you consume less tokens but more expensive tokens?

As for context size and harnesses I did make a trivial bash agent based on this "agent in 50 lines" tutorial[0] recently, and found that for trivial work, it was about an order of magnitude cheaper and faster.

I haven't tested it on anything bigger but it doesn't seem to do the kind of proactive testing, that they do in bigger harnesses.

Codex at least has a system prompt that tells it not to consider a feature a complete until it has verified it. I'm not sure about Claude Code.

I suppose I could add that one line to the prompt, and it would get me much closer to agi :) I think Fable does this proactively even without a prompt, but I haven't tested that yet.

If Fable in my own harness is significantly cheaper than Claude Code, that would be very appealing. (I could actually afford to use it for most things!) But I think most of the cost comes from the testing it does. So we'll have to see.

[0] https://minimal-agent.com/

Fable's subscription inclusion theoretically ends EOD today. Anthropic put a wishy-washy "if we have capacity we'll continue it" thing, and given how competitive GPT 5.6 Sol is, and it is included in OpenAI's subscription, I fully expect Anthropic to extend Fable or they will have a serious exodus on their hands.

Competition is good.

> and on-device model combination right now

That would depend entirely on what your device is. This sounds likely not to be an issue with the harness, but the capabilities of the models you've tried.

I experience almost no tool call failure using my nothing-special harness and DSv4 Flash.

You can't afford the best model. What are your specs and what models + quants have you tried?

Qwen 3.6 35B A3B and Qwen 3.6 27B can both do reliable tool calls on Pi at Q4_K_M using llama.cpp

Well, I have to open the lid on my computer and remember my password, no?

Anecdotally, the results from OpenCode + Claude appear to be the same if not better for our uses over the past year.

GLM isn't good enough yet.

It pays to be marginally ahead of people stuck on open models.

The Sleev (the project has been renamed to make a startup) creator was shilling their project in the OpenCode Discord. That person is very convinced they have something that no one has ever built before. They focused on token reduction without any real evals for capability impacts.

I'm generally against this context pruning without prompting or details. Sleev is very opaque about how it works and definitely will bust your cache.

OpenAI, to their credit, seems to be focusing pretty heavily on token efficiency in GPT 5.5 and beyond.

Given they're incentivized to increase token use, what guarantees that higher token use improves the effectiveness of the agent and isn't just artificial padding?

Is there evidence that it is actually a better agent though?

Model:

Cost, mainly. The runs went through a Claude Max subscription rather than metered API billing, and pinning an older stable snapshot kept run-to-run comparisons clean and cheap. The fixed harness payload (system prompt plus tool schemas), so the headline numbers shouldn't change too much.

That said, happy to re-run the matrix on Fable and publish the diff; payload figures should barely move, tool-calling behaviour might.

Gateway:

Meridian (github.com/rynfar/meridian); proxy that bridges the Claude Code SDK to a standard Anthropic endpoint so a Claude Max subscription can drive OpenCode-et-al.

It's the auth route for all agent traffic on the machine, not something built for the benchmark.